A Perception-Driven Autonomous Urban Vehicle

The DARPA Urban Challenge, 2009

PDF thumbnail
(PDF, 2.6 MB )

Abstract

This paper describes the architecture and implementation of an autonomous passenger vehicle designed to navigate using locally perceived information in preference to potentially inaccurate or incomplete map data. The vehicle architecture was designed to handle the original DARPA Urban Challenge requirements of perceiving and navigating a road network with segments defined by sparse waypoints. The vehicle implementation includes many heterogeneous sensors with significant communications and computation bandwidth to capture and process high-resolution, high-rate sensor data. The output of the comprehensive environmental sensing subsystem is fed into a kino-dynamic motion planning algorithm to generate all vehicle motion. The requirements of driving in lanes, three-point turns, parking, and maneuvering through obstacle fields are all generated with a unified planner. A key aspect of the planner is its use of closed-loop simulation in a Rapidly-exploring Randomized Trees (RRT) algorithm, which can randomly explore the space while efficiently generating smooth trajectories in a dynamic and uncertain environment. The overall system was realized through the creation of a powerful new suite of software tools for message-passing, logging, and visualization. These innovations provide a strong platform for future research in autonomous driving in GPS-denied and highly dynamic environments with poor a priori information.


bibtex

@incollection{mitduc2009,
    YEAR       = {2009},
    ISBN       = {978-3-642-03990-4},
    BOOKTITLE  = {The DARPA Urban Challenge},
    VOLUME     = {56},
    SERIES     = {Springer Tracts in Advanced Robotics},
    EDITOR     = {Buehler, Martin and Iagnemma, Karl and Singh, Sanjiv},
    DOI        = {10.1007/978-3-642-03991-1_5},
    TITLE      = {A Perception-Driven Autonomous Urban Vehicle},
    URL        = {http://dx.doi.org/10.1007/978-3-642-03991-1_5},
    PUBLISHER  = {Springer Berlin Heidelberg},
    AUTHOR     = {John Leonard and Jonathan How and Seth Teller and Mitch Berger and
                 Stefan Campbell and Gaston Fiore and Luke Fletcher and Emilio Frazzoli
                 and Albert Huang and Sertac Karaman and Olivier Koch and Yoshiaki
                 Kuwata and David Moore and Edwin Olson and Steve Peters and Justin Teo
                 and Robert Truax and Matthew Walter and David Barrett and Alexander
                 Epstein and Keoni Maheloni and Katy Moyer and Troy Jones and Ryan
                 Buckley and Matthew Antone and Robert Galejs and Siddhartha
                 Krishnamurthy and Jonathan Williams},
    PAGES      = {163-230},
}